U-M startup tracks social distancing using public street cameras around the globe

Video-based tool monitors high-traffic areas and their response to the coronavirus pandemic


ANN ARBOR, Mich. – A University of Michigan startup, Voxel51, is using data from public street cameras to track social distancing behaviors around the world amid the coronavirus (COVID-19) pandemic.

The startup announced Wednesday that its new tool uses the camera footage and computer vision models to track vehicle, cyclist and pedestrian traffic at New York’s Times Square; Abbey Road in London; Fremont Street in downtown Las Vegas; Seaside Heights in New Jersey; a beach in Fort Lauderdale and intersections in Dublin and Prague.

“This pandemic is having an unprecedented impact on our daily lives and what we’re trying to do is create a tool to improve public awareness,” said Jason Corso, U-M professor of electrical and computer engineering and CEO of Voxel51, an Ann Arbor video analytics and data management company.

Users can select a specific point in time at a specific location and view historic footage, policies in the area such as school closures or stay-at-home orders, case rates and death rates. Researchers are in the process of adding additional locations and types of data, such as weather, officials said.

Voxel51′s tool tracks social distancing behaviors in real time and assigns each location a physical distancing index (PDI score) every 15 minutes.

“The PDI score helps people understand and compare how the coronavirus is changing social behaviors over time and enables municipalities to visualize how they’re doing from a public health perspective," Corso said. "Even though the virus is spreading, overall, we can see that the public response to the stay-at-home mandates has been rather dramatic and impressive.”

The tool’s graphs have offered insight into the difficulty of limiting human interaction, especially in the event of good weather and special celebrations, officials said.

Voxel51 reports that crowds in Fort Lauderdale were at all-time highs in early March during spring break, despite the state declaring a public emergency at the end of February. Their data also highlights an uptick in public gathering on St. Patrick’s Day in Dublin.

The startup claims their tool is unique in that it’s real time, video-based and protects privacy -- while data sources like mobile phones don’t protect privacy and offer only approximate locations, officials said.

Voxel51 says it is accepting requests to add specific locations or installations for local government and taxpayer usage. The data could be especially helpful to residents to identify the traffic in an area before traveling there.

“We expect to find rich information in the joint analysis of the physical distancing index and these other feeds,” Corso said. “There is even a chance that the PDI can feed into a predictive model for cities not yet greatly affected and the potential for a renewed outbreak next year.”

Read our latest updates on the COVID-19 pandemic here.

About the Author:

Cassidy Johncox is a senior digital news editor covering stories across the spectrum, with a special focus on politics and community issues.